Congress on Evolutionary Computation. Washington, DC, 6-9 July 1999. ; Neural networks (NN) can be used as controllers in autonomous robots. The specific features of the navigation problem in robotics make generation of good training sets for the NN difficult. An evolution strategy (ES) is introduced to learn the weights of the NN instead of the learning method of the network. The ES is used to learn high performance reactive behavior for navigation and collision avoidance. No subjective information about “how to accomplish the task” has been included in the fitness function. The learned behaviors are able to solve the problem in different environments; therefore, the learning process has the proven ability to obtain a specialized behavior. All the behaviors obtained have been tested in a set of environments and the capability of generalization is shown for each learned behavior. A simulator based on the mini-robot, Khepera, has been used to learn each behavior.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Neural networks robot controller trained with evolution strategies



    Erscheinungsdatum :

    1999-07-01



    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Schlagwörter :

    Klassifikation :

    DDC:    629



    An On-Line Trained Adaptive Neural Controller

    Zhang, Y. / Sen, P. / Hearn, G. E. | British Library Online Contents | 1995


    Ship motion control by an on-line trained neural controller

    Hearn, G. E. / Sen, P. / Zhang, Y. et al. | British Library Conference Proceedings | 1994


    Neural Network Trained Controller for Atmospheric Entry in Mars Missions

    Wang, Hao / Martin, Dillon / Elgohary, Tarek | TIBKAT | 2019


    Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks

    Jin, Junqi / Fu, Kun / Zhang, Changshui | IEEE | 2014


    Neural networks trained with WiFi traces to predict airport passenger behavior

    Orsini, Federico / Gastaldi, Massimiliano / Mantecchini, Luca et al. | IEEE | 2019